Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 15604
    Prev
    Next
    INDEX
    Explanations

    emotions related to fear, anger, and animosity in contexts of protest or conflict

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    negative emotions

    np_acts-logits-general · gemini-2.0-flash

    strong negative sentiments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ItemLayout
    -0.54
     rowspan
    -0.49
    CodedInputStream
    -0.47
    brigens
    -0.47
    MemoryWarning
    -0.46
     asal
    -0.45
    VersionUID
    -0.45
     zp
    -0.45
    ArrowToggle
    -0.44
    ständ
    -0.43
    POSITIVE LOGITS
     expressed
    0.97
     aroused
    0.89
    expressed
    0.80
     voiced
    0.78
     fuelled
    0.77
     engendered
    0.76
     fueled
    0.75
     generated
    0.73
     kindled
    0.73
     felt
    0.70
    Activations Density 0.293%

    No Known Activations